Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 614 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4899. Min Act: -0.0000

Data Index: 389307 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1389826 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4774. Min Act: 0.0000

Data Index: 228004 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4266. Min Act: 0.0000

Data Index: 78363 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1464397 (Python Code)

Max Activating Token Index: 542

Text #5

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3827. Min Act: -0.0000

Data Index: 27873 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4527. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4020. Min Act: -0.0000

Data Index: 22230 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1653733 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3751. Min Act: -0.0000

Data Index: 782445 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1539719 (Python Code)

Max Activating Token Index: 596

Text #11

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1213374 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3827. Min Act: -0.0000

Data Index: 633926 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3606. Min Act: -0.0000

Data Index: 647846 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1284058 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3343. Min Act: -0.0000

Data Index: 837224 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1059160 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3571. Min Act: -0.0000

Data Index: 826615 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3373. Min Act: -0.0000

Data Index: 50741 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.5125. Min Range: -0.5125

Max Act: 0.3757. Min Act: -0.0000

Data Index: 499573 (C4 (Web Text))

Max Activating Token Index: 492